Hugging Face's logo

rpreite
/
Gemma3_AWQ_W4A16_no_128

Safetensors
Model card Files
xet
 Community
Gemma3_AWQ_W4A16_no_128
File size: 5,512 Bytes
7c4707f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
{
  "architectures": [
    "Gemma3ForConditionalGeneration"
  ],
  "boi_token_index": 255999,
  "eoi_token_index": 256000,
  "eos_token_id": [
    1,
    106
  ],
  "image_token_index": 262144,
  "initializer_range": 0.02,
  "mm_tokens_per_image": 256,
  "model_type": "gemma3",
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "pack-quantized",
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 128,
          "num_bits": 4,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "group",
          "symmetric": true,
          "type": "int"
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "model.vision_tower.vision_model.encoder.layers.0.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.1.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.2.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.3.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.4.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.5.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.6.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.7.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.8.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.9.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.10.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.11.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.12.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.13.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.14.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.15.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.16.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.17.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.18.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.19.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.20.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.21.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.22.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.23.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.24.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.25.mlp.fc2",
      "model.vision_tower.vision_model.encoder.layers.26.mlp.fc2",
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.11.0"
  },
  "text_config": {
    "_sliding_window_pattern": 6,
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_logit_softcapping": null,
    "final_logit_softcapping": null,
    "head_dim": 256,
    "hidden_activation": "gelu_pytorch_tanh",
    "hidden_size": 3840,
    "initializer_range": 0.02,
    "intermediate_size": 15360,
    "layer_types": [
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention"
    ],
    "max_position_embeddings": 131072,
    "model_type": "gemma3_text",
    "num_attention_heads": 16,
    "num_hidden_layers": 48,
    "num_key_value_heads": 8,
    "query_pre_attn_scalar": 256,
    "rms_norm_eps": 1e-06,
    "rope_local_base_freq": 10000.0,
    "rope_scaling": {
      "factor": 8.0,
      "rope_type": "linear"
    },
    "rope_theta": 1000000.0,
    "sliding_window": 1024,
    "use_cache": true,
    "vocab_size": 262208
  },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.55.2",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "image_size": 896,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 27,
    "patch_size": 14,
    "vision_use_head": false
  }
}